Skip to main content
Glama
dcondrey

cogmem

by dcondrey
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to cogmem

  • Codex Memory

    zhangtian-123
    A
    license
    B
    quality
    D
    maintenance
    Local Markdown-backed memory tools for Codex and other MCP-capable agents. Exposes durable agent knowledge via CLI and MCP server.
    5
    MIT

  • Linksee Memory

    michielinksee
    A
    license
    A
    quality
    A
    maintenance
    Hand a project over — to your next session, to Cursor/Codex/Gemini, to your successor — with the reasons attached. Local-first memory MCP for coding agents: decisions re-injected before the agent acts, drift detection across every project you run. One SQLite file, nothing leaves your machine.
    8
    69 npm
    14
    MIT

  • repo-memory

    yubinkim444
    A
    license
    A
    quality
    C
    maintenance
    A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep
    5
    27 PyPI
    1
    MIT

Related Servers

  • Projectmem

    riponcm
    A
    license
    A
    quality
    A
    maintenance
    Local-first memory layer for AI coding agents — captures issues, attempts, fixes, and decisions, and warns at git commit before you repeat a mistake.
    17
    330 PyPI
    833
    MIT

  • memini

    lumayapartners
    A
    license
    A
    quality
    B
    maintenance
    Local-first project memory for AI coding agents. Records failed attempts, fragile files, and decisions per repo, and warns the agent via hooks before it repeats a recorded mistake.
    6
    42 npm
    MIT

  • Nahuali

    Arakiss
    F
    license
    Not graded
    quality
    A
    maintenance
    Local-first memory for AI agents with evidence-backed recall, deterministic trust verdicts, self-inspection, and a tamper-evident audit history.
    3
    -
  • @team-monet/monet by team-monet

    @team-monet/monetofficial

    team-monet
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides a local-first memory layer for coding agents, storing principles, rules, and corrections on-device and surfacing them at the moments they apply so agents act on the intended outcomes without sending data to the cloud.
    18,420 npm
    1
    AGPL 3.0

  • ProactiveAgent

    ConradLu2740
    A
    license
    A
    quality
    A
    maintenance
    Provides shared long-term memory and proactive suggestions across AI coding agents, enabling persistent user preferences and behavior rules that are remembered and applied across different tools. Includes memory capture, recall, extraction, and suggestion tools with a local-first and privacy-focused design.
    20
    1
    MIT
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.6/5.0

Scored across 8 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: note saves memories, recall retrieves them, progress summarizes project state, receipt provides cryptographic proofs, review_pending lists pending rules, status reports system health, tree_head returns the Merkle root, and verify performs deep audit. No overlapping functionality.

Naming Consistency5/5

All tool names are lowercase with underscores for compounds (e.g., review_pending, tree_head). They follow a consistent pattern of verbs or noun phrases that clearly indicate the action or output, with no style mixing.

Tool Count5/5

With 8 tools, the set is well-scoped for a verifiable memory system. It covers storing, retrieving, verifying, and monitoring without being bloated or too sparse.

Completeness4/5

The tools provide core operations (create, read, verify, audit). Missing explicit update/delete tools is a minor gap, but this aligns with the system's append-only, tamper-evident design. A tool for exact-match retrieval could be useful, but semantic recall covers most needs.

Maintenance

ActivityMaintained
ResponsivenessResponsive

Resources